Skill ディレクトリ

AI Agent のための再利用可能な Skill を見つける。

タスクで実際の GitHub Skill を検索し、利用前に Stars、Trust、監査、カテゴリ、インストール経路を確認できます。

すべての推奨は、リポジトリ、監査、インストール経路に明確につながっています。

検索結果: expression-tree

英語版ディレクトリ

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

14K
Stars
80/100
信頼
カテゴリ: agent-frameworks監査

A fast, distributed, high performance gradient boosting (GBT, GBDT, GBRT, GBM or MART) framework based on decision tree algorithms, used for ranking, classification and many other machine learning tasks.

18K
Stars
87/100
信頼
カテゴリ: ml-automation監査
Sem84

Semantic version control => entity-level diffs, blame, and impact analysis on top of git. 26 languages via tree-sitter. Built for coding agents.

3.2K
Stars
84/100
信頼
カテゴリ: agent-frameworks監査

Crabbox: warm a box, sync the diff, run the suite.

1.3K
Stars
81/100
信頼
カテゴリ: utility監査

6,100+ brand SVG icons for developers. Tree-shakeable, typed, open source. npm i thesvg

2.4K
Stars
84/100
信頼
カテゴリ: agent-skills監査
Evo84

turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then runs tree search with parallel subagents.

1.2K
Stars
84/100
信頼
カテゴリ: agent-skills監査

A Claude Code plugin that provides a universal radial-tree exploration engine with swappable presets for divergent ideation, adversarial critique, design-space exploration, and code audit.

161
Stars
76/100
信頼
カテゴリ: coding-agents監査

A lightweight configuration/utility that prevents coding agents like Codex and Claude Code from over-engineering tasks with unnecessary modules, subagents, dependencies, and hashes.

141
Stars
77/100
信頼
カテゴリ: coding-agents監査

Glisp is a Lisp-based design tool that combines generative approaches with traditional design methods, empowering artists to discover new forms of expression.

1.2K
Stars
80/100
信頼
カテゴリ: design-creative監査

Automated Cherry Studio review for local branches, PRs, commits, files, architecture docs, and repository skills. Use for code or documentation reviews that need project-specific naming, main/renderer/shared placement and dependency rules, IpcApi and DataApi boundaries, lifecycle/service ownership, renderer hooks, React/UI conventions, and tests. Supports single-agent review with interactive fix selection or multi-agent reviewer-verifier review with risk-based auto-fix. To diagnose gaps in the skill after a review session, run `/gh-pr-review diag`.

51K
Stars
79/100
信頼
カテゴリ: research監査

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

51K
Stars
68/100
信頼
カテゴリ: design-creative監査